mm: ZERO_PAGE without PTE_SPECIAL

Reinstate anonymous use of ZERO_PAGE to all architectures, not just to
those which __HAVE_ARCH_PTE_SPECIAL: as suggested by Nick Piggin.

Contrary to how I'd imagined it, there's nothing ugly about this, just a
zero_pfn test built into one or another block of vm_normal_page().

But the MIPS ZERO_PAGE-of-many-colours case demands is_zero_pfn() and
my_zero_pfn() inlines.  Reinstate its mremap move_pte() shuffling of
ZERO_PAGEs we did from 2.6.17 to 2.6.19?  Not unless someone shouts for
that: it would have to take vm_flags to weed out some cases.

Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Rik van Riel <riel@redhat.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 1a9f9b257551cdf7dcda29b2adce5dd0dfe69a86..d6eb6134abeca4f819427937c9ad3dee380d1360 100644 (file)
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -76,6 +76,16 @@ extern unsigned long zero_page_mask;
 #define ZERO_PAGE(vaddr) \
        (virt_to_page((void *)(empty_zero_page + (((unsigned long)(vaddr)) & zero_page_mask))))
 
+#define is_zero_pfn is_zero_pfn
+static inline int is_zero_pfn(unsigned long pfn)
+{
+       extern unsigned long zero_pfn;
+       unsigned long offset_from_zero_pfn = pfn - zero_pfn;
+       return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
+}
+
+#define my_zero_pfn(addr)      page_to_pfn(ZERO_PAGE(addr))
+
 extern void paging_init(void);
 
 /*

diff --git a/mm/memory.c b/mm/memory.c
index 5c694f2b9c12d02d6a9ca129afb702d68237a9c9..9bdbd10cb4188baa8b2200e5570f371a7749d553 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -108,7 +108,7 @@ static int __init disable_randmaps(char *s)
 }
 __setup("norandmaps", disable_randmaps);
 
-static unsigned long zero_pfn __read_mostly;
+unsigned long zero_pfn __read_mostly;
 
 /*
  * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init()
@@ -455,6 +455,20 @@ static inline int is_cow_mapping(unsigned int flags)
        return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 }
 
+#ifndef is_zero_pfn
+static inline int is_zero_pfn(unsigned long pfn)
+{
+       return pfn == zero_pfn;
+}
+#endif
+
+#ifndef my_zero_pfn
+static inline unsigned long my_zero_pfn(unsigned long addr)
+{
+       return zero_pfn;
+}
+#endif
+
 /*
  * vm_normal_page -- This function gets the "struct page" associated with a pte.
  *
@@ -512,7 +526,7 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
                        goto check_pfn;
                if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
                        return NULL;
-               if (pfn != zero_pfn)
+               if (!is_zero_pfn(pfn))
                        print_bad_pte(vma, addr, pte, NULL);
                return NULL;
        }
@@ -534,6 +548,8 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
                }
        }
 
+       if (is_zero_pfn(pfn))
+               return NULL;
 check_pfn:
        if (unlikely(pfn > highest_memmap_pfn)) {
                print_bad_pte(vma, addr, pte, NULL);
@@ -1161,7 +1177,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
        page = vm_normal_page(vma, address, pte);
        if (unlikely(!page)) {
                if ((flags & FOLL_DUMP) ||
-                   pte_pfn(pte) != zero_pfn)
+                   !is_zero_pfn(pte_pfn(pte)))
                        goto bad_page;
                page = pte_page(pte);
        }
@@ -1443,10 +1459,6 @@ struct page *get_dump_page(unsigned long addr)
        if (__get_user_pages(current, current->mm, addr, 1,
                        FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma) < 1)
                return NULL;
-       if (page == ZERO_PAGE(0)) {
-               page_cache_release(page);
-               return NULL;
-       }
        flush_cache_page(vma, addr, page_to_pfn(page));
        return page;
 }
@@ -1629,7 +1641,8 @@ int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
         * If we don't have pte special, then we have to use the pfn_valid()
         * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must*
         * refcount the page if pfn_valid is true (hence insert_page rather
-        * than insert_pfn).
+        * than insert_pfn).  If a zero_pfn were inserted into a VM_MIXEDMAP
+        * without pte special, it would there be refcounted as a normal page.
         */
        if (!HAVE_PTE_SPECIAL && pfn_valid(pfn)) {
                struct page *page;
@@ -2097,7 +2110,7 @@ gotten:
        if (unlikely(anon_vma_prepare(vma)))
                goto oom;
 
-       if (pte_pfn(orig_pte) == zero_pfn) {
+       if (is_zero_pfn(pte_pfn(orig_pte))) {
                new_page = alloc_zeroed_user_highpage_movable(vma, address);
                if (!new_page)
                        goto oom;
@@ -2658,8 +2671,9 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
        spinlock_t *ptl;
        pte_t entry;
 
-       if (HAVE_PTE_SPECIAL && !(flags & FAULT_FLAG_WRITE)) {
-               entry = pte_mkspecial(pfn_pte(zero_pfn, vma->vm_page_prot));
+       if (!(flags & FAULT_FLAG_WRITE)) {
+               entry = pte_mkspecial(pfn_pte(my_zero_pfn(address),
+                                               vma->vm_page_prot));
                ptl = pte_lockptr(mm, pmd);
                spin_lock(ptl);
                if (!pte_none(*page_table))